@davila7

scikit-survival covers cox models, ensemble methods, and svms for censored time-to-event data. includes decision trees for model selection, multiple evaluation metrics accounting for censoring levels, and four end-to-end workflows from data prep through model comparison.

motion-canvas covers programmatic video creation in typescript with numbered setup steps, esmcommonjs workarounds, and concrete troubleshooting for vite plugin configuration issues.

skill-developer provides actionable guidance for building claude code skills with hook architecture, trigger configuration, and enforcement patterns. covers skill-rules.json setup, guardrail vs domain skill types, and testing procedures.

receiving-code-review guides technical evaluation of feedback before implementation, emphasizing verification over performative agreement and teaching when to push back with reasoned skepticism.

test-driven-development prescribes writing failing tests before implementation code, following red-green-refactor cycles. covers new features, bug fixes, refactoring, and behavior changes with explicit guardrails against common rationalizations.

davila7-instructor covers pydantic-based structured output extraction from llm responses with automatic validation, retry logic, and streaming support across anthropic and openai providers.

writing-clearly-and-concisely applies strunk's rules for grammar, voice, and concision to human-facing prose, with explicit patterns to avoid in ai-generated text.

bigcode evaluation harness benchmarks code generation models across 15+ datasets including humaneval, mbpp, and multipl-e with pass@k metrics. covers single and multi-language evaluation, instruction-tuned models, and model comparison workflows.

finishing-a-development-branch verifies test status, presents four concrete options for integrating completed work, and executes the chosen path with appropriate cleanup, handling both local merge and pull request workflows.

commit-work guides staged, logically scoped commits with clear messages. covers workflow from inspection through verification, enforces conventional commits, and requires explicit what/why reasoning before each message.

nowait-reasoning-optimizer suppresses self-reflection tokens during inference to reduce chain-of-thought output length by 27-51% across r1-style reasoning models, with trade-offs between token savings and distilled model accuracy.

davila7-ml-paper-writing guides end-to-end paper drafting for top-tier ML conferences (NeurIPS, ICML, ICLR, ACL, AAAI, COLM). centers on citation verification workflows, narrative clarity principles, and iterative feedback loops with explicit deployment of proactive drafting over blocking.

railway-database deploys postgres, redis, mysql, or mongodb templates into railway projects. checks for existing databases first, then provisions with volumes and connection variables. connects services via reference syntax or manual wiring.

davila7-copywriting covers marketing copy for web pages (homepages, landing pages, pricing, feature, about). provides headline formulas, copywriting principles (clarity, benefits, specificity), section frameworks, and guidance for cta copy and page-specific strategies.

davila7-docker-expert covers dockerfile optimization, multi-stage builds, container security hardening, docker compose orchestration, and image size reduction. practical, code-heavy patterns for production deployment. handoff logic clear for kubernetes and ci/cd boundaries.

paid-ads covers strategy, creative, and targeting across google, meta, linkedin, twitter, and tiktok. includes campaign structure, audience segmentation, retargeting funnels, and optimization levers with platform-specific setup checklists.

davila7-gh-fix-ci inspects github actions failures on pull requests, fetches logs, and proposes fixes after user approval. handles github actions only, explicitly out-of-scope for external ci systems like buildkite.

pentest-checklist provides a phased workflow covering scope definition, environment preparation, expertise selection, monitoring, and remediation. includes pre/post checklists, threat enumeration, vendor policies, and remediation procedures.

langfuse covers llm observability via tracing, prompt versioning, and evaluation. provides openai and langchain integrations with practical patterns for cost and quality monitoring in production systems.

viral-generator-builder covers architecture for shareable generator tools including quizzes, name generators, and avatar creators. focuses on minimal input design, screenshot-optimized results, and identity-driven sharing mechanics.

tensorboard covers metric visualization, model debugging, experiment comparison, and performance profiling for pytorch and tensorflow workflows. includes embedding projection, hyperparameter tracking, and multi-run dashboard analysis.

audiocraft-audio-generation covers meta's pytorch library for generating music and sound effects from text, with model variants ranging from 300m to 3.3b parameters, melody conditioning, stereo support, and style transfer capabilities.

marp-slide covers slide creation across 7 themes with template selection logic, syntax guidance, and quality checklists. procedurally sound for standard workflows, but lacks explicit handling of common failure modes like malformed markdown or missing asset files.

railway-status queries deployment state and service health for railway projects, parsing cli output to surface project name, environment, service status, active deployments, and configured domains.

davila7-api-fuzzing-for-bug-bounty covers reconnaissance, authentication testing, idor exploitation, injection attacks, and graphql-specific vectors with concrete payloads and tool references, but lacks decision logic for determining when to escalate findings or adjust testing strategy based on responses.

davila7-web-quality-audit provides structured guidance across four audit domains (performance, accessibility, seo, best practices) with detailed checks and severity classification, but lacks executable steps and failure-mode handling.

api-security-best-practices covers authentication, authorization, input validation, and rate limiting with working code examples. practical but lacks systematic treatment of failure modes and recovery patterns across all security domains.

davila7-writing-clearly-and-concisely applies strunk's elements of style and ai pattern detection to improve prose for documentation, commits, ui text, and reports. covers grammar, composition principles, and anti-patterns to avoid.

schema-markup provides reference templates for common schema.org types (organization, article, product, event, faq) with json-ld examples and validation guidance. covers implementation patterns for static and dynamic sites.

qms-audit-expert provides iso 13485 audit program management, risk-based planning, and auditor competency frameworks for medical device organizations. covers audit execution, external audit preparation, and capa integration with supporting templates and checklists.

railway-templates enables searching and deploying pre-configured services from railway's marketplace via graphql queries. covers common databases, cms platforms, and automation tools with template lookup and deployment workflows.

lint-and-validate enforces post-modification quality gates across node.js and python ecosystems, combining linting, type checking, and security audits into a mandatory validation loop.

roier-seo runs lighthouse audits on websites or localhost and surfaces performance, accessibility, seo, and core web vitals scores. includes templated fixes for common issues like meta tags and structured data.

davila7-launch-strategy structures product launches across five phases (internal through full launch) with emphasis on owned, rented, and borrowed channels. covers product hunt preparation, post-launch retention, and ongoing momentum tactics but lacks concrete failure mode handling and decision trees for real-world constraints.

scientific-brainstorming structures ideation through five phases (context, divergence, connection, evaluation, synthesis), offering conversational techniques for hypothesis generation, cross-domain reasoning, and methodological exploration. best suited for researchers seeking structured creative problem-solving without computational constraints.

davila7-seo-optimizer covers keyword research, on-page optimization, technical seo implementation, and core web vitals tuning. comprehensive reference material but lacks decision logic and failure recovery patterns.

davila7-seo-audit provides a comprehensive framework for diagnosing seo problems across technical, on-page, and content dimensions. lacks procedural depth and concrete decision logic for translating findings into prioritized action.

davila7-design-system-starter provides token structures, atomic design methodology, and accessibility baseline for building consistent ui systems. lacks concrete procedures for implementation and assumes significant prior design system knowledge.

davila7-nextjs-best-practices covers app router fundamentals including server vs client component selection, data fetching caching layers, and routing file conventions. reference material for architectural decisions rather than executable workflow.

web-artifacts-builder provides a scripted workflow for generating self-contained react artifacts with tailwind css and shadcn/ui components, bundled into single html files for claude.ai display.

davila7-scientific-visualization covers matplotlib, seaborn, and plotly workflows for creating journal-ready plots. includes style presets, colorblind-safe palettes, multi-panel layouts, and export utilities for pdf/eps/tiff, but lacks explicit failure handling and edge case recovery paths.

notion-spec-to-implementation converts product specs into linked notion plans and task databases, with structured parsing, templated artifacts, and progress tracking cadence.

bash-linux is a reference guide covering core linux utilities, command chaining, process management, and scripting patterns. organized as lookup tables with examples rather than goal-driven procedures.

competitor-alternatives covers four page formats (singular alternative, plural alternatives roundup, you vs competitor, head-to-head) with centralized competitor data architecture, templated sections for features/pricing/support, and index pages for SEO consolidation. execution guidance is strategic but lacks step-by-step task breakdowns.

design-system-starter provides token structures, atomic component patterns, and wcag 2.1 guidelines for building consistent design systems. content is heavy on definitions and examples but light on implementation workflows.

railway-projects manages project lifecycle operations: listing, switching between projects, and configuring settings like visibility, pr deploys, and naming via railway cli and graphql mutations.

requesting-code-review guides developers to dispatch a code-reviewer subagent at defined checkpoints (task completion, feature milestones, pre-merge) with git SHAs and structured context, then act on severity-tiered feedback.

davila7-create-plan generates structured coding task plans from user requests by scanning context, asking minimal follow-ups, and delivering a templated action checklist with scope boundaries and open questions.

davila7-agent-memory-mcp provides four mcp tools (search, write, read, stats) for persistent agent memory backed by project docs. setup is npm-based, dashboard included, but lacks failure handling and clear decision logic.

tdd-workflow covers the red-green-refactor cycle and three laws of tdd. includes phase principles, the aaa test pattern, prioritization guidance, and anti-patterns to avoid.

telegram-bot-builder covers bot architecture, api integration, and monetization patterns for telegram. includes code examples for commands, keyboards, and payments, but lacks depth on failure modes and production concerns.

scroll-experience covers parallax storytelling, scroll-triggered animations, and cinematic web patterns using gsap, framer motion, and css scroll-timeline. includes anti-patterns and mobile considerations but lacks concrete decision trees.

davila7-bash-linux is a reference sheet of common bash commands and patterns for linux/macos, organized by category (file ops, process management, text processing). useful as lookup material but lacks procedural guidance for actual task execution.

quality-manager-qms-iso13485 covers iso 13485 implementation, document control, internal audits, design controls, and supplier management. references external templates and scripts without integrating concrete procedures or decision logic into the skill itself.

meeting-insights-analyzer extracts communication patterns from transcripts, surfacing conflict avoidance, speaking ratios, and filler word usage with timestamped examples. execution depends entirely on claude code's transcript parsing and pattern matching capabilities.

discord-bot-architect provides discord.js v14 and pycord patterns for slash commands and gateway intents, but lacks complete procedural depth and edge case treatment needed for production robustness.

uspto-database aggregates patent and trademark search, examination history via peds, assignments, citations, and litigation records through multiple specialized apis. covers portfolio analysis and prior art research across 8+ endpoints with python helper scripts.

davila7-scientific-critical-thinking covers methodology critique, bias detection, statistical analysis evaluation, and evidence quality assessment using GRADE and Cochrane frameworks. however, it lacks actionable decision points and concrete trigger conditions for when to apply specific sub-skills.

davila7-email-systems covers transactional email queuing, deliverability infrastructure (spf/dkim/dmarc), and event tracking. identifies common failure modes but lacks concrete implementation steps and decision trees.

davila7-red-team-tools-and-methodology covers subdomain enumeration, host discovery, technology fingerprinting, and vulnerability scanning using industry tools. workflow-heavy but lacks decision logic and failure recovery patterns.

davila7-ui-ux-pro-max is a reference guide for UI/UX patterns across 9 stacks, offering design system generation via Python CLI. breadth of coverage (styles, palettes, fonts) is extensive but execution depends entirely on external script behavior and database contents, neither documented here.

security-scanning-tools catalogs command syntax and workflows for nmap, masscan, nessus, burp suite, zap, nikto, aircrack-ng, clamav, and compliance scanners. heavy on tool reference, light on decision logic and failure recovery.

sql-injection-testing covers vulnerability assessment across in-band, blind, and out-of-band attack vectors using proxy tools and sqlmap. lacks procedural detail and failure handling.

bioservices wraps 40+ bioinformatics web services (uniprot, kegg, chembl, pubchem, reactome, quickgo) under a unified python api. handles rest and soap protocols transparently for cross-database workflows and identifier mapping.

computer-use-agents covers building vision-guided automation loops that perceive screens, reason about actions, and execute mouse/keyboard commands. includes sandboxing patterns and anthropic's official implementation with tool definitions.

theme-factory applies one of 10 curated color and font themes to presentation artifacts. supports custom theme generation when presets don't fit. lacks operational detail on implementation mechanics.

nextjs-supabase-auth covers supabase integration with next.js app router, emphasizing middleware token handling and server/client boundary awareness, but lacks concrete implementation steps and failure mode documentation.

move-code-quality provides a comprehensive checklist for analyzing move language packages against 2024 edition standards. the skill maps 11 categories of code patterns with specific rules but lacks executable workflow clarity and error handling guidance.

hqq-quantization enables calibration-free weight quantization across 8/4/3/2/1-bit precision levels with multiple backend optimizations, designed for rapid model compression without sample datasets.

evaluating-llms-harness provides a command-line interface to benchmark language models against 60+ academic tasks like mmlu and gsm8k. lacks guidance on interpreting results, comparing models, or handling common failure modes.

davila7-citation-management covers paper search (google scholar, pubmed), metadata extraction from dois/pmids/arxiv, bibtex formatting and validation. heavily bash-script dependent with minimal error handling.

davila7-database-design covers schema design, orm selection, and indexing strategy via a modular content map. emphasizes context-driven decision-making over pattern copying, but lacks executable procedures and failure mode guidance.

sparse-autoencoder-training covers sae training via saelens for decomposing neural network activations into interpretable sparse features, with background on polysemanticity and superposition but incomplete procedural guidance.

scikit-bio provides sequence parsing, alignment, phylogenetic tree construction, and ecological statistics (alpha/beta diversity, UniFrac, PCoA, PERMANOVA) for bioinformatics workflows. covers DNA/RNA/protein data and multiple biological file formats.

transformer-lens-interpretability documents the mechanistic interpretability library for inspecting transformer internals via hookpoints, reverse-engineering learned algorithms, and performing activation patching experiments.

geo-database documents ncbi geo's data hierarchy and use cases for gene expression research, but lacks concrete procedural steps, api endpoints, or executable workflows for actual dataset retrieval.

implementing-llms-litgpt documents model loading and basic setup using litgpt's pretrained architectures, but lacks training workflows, validation procedures, and failure handling details.

image-enhancer upscales and sharpens screenshots and photos for presentations, documentation, and social media. it analyzes resolution and compression artifacts, then applies enhancement filters and outputs optimized files while preserving originals.

prompt-caching covers caching strategies for LLM cost reduction, including anthropic prompt caching, response caching, and cache augmented generation patterns with identified anti-patterns and sharp edges.

clean-code documents pragmatic coding principles (srp, dry, kiss, yagni) with naming conventions and function rules. lacks concrete implementation guidance and trigger phrases for actual coding tasks.

scroll-experience covers parallax, scroll animations, and sticky sections with code examples across gsap, framer motion, and css. lacks procedural depth for actual implementation and glosses over mobile/performance constraints.

davila7-app-store-optimization describes aso capabilities across keyword research, metadata optimization, and review analysis, but lacks actionable procedures and concrete decision logic to execute the claimed toolkit functions.

scientific-slides guides presentation creation using nano banana pro for image generation and pdf assembly, with formatting consistency protocols for multi-slide decks. covers workflows for pdf slides and powerpoint integration but lacks actionable decision logic and failure recovery.

davila7-page-cro provides a diagnostic framework for analyzing marketing pages and suggests optimization levers across value prop, headlines, ctas, and trust signals. lacks executable procedures and concrete decision logic.

game-changing-features prompts strategic product thinking by reframing questions around 10x value creation rather than incremental improvement, routing output to session documents for founder-level analysis.

biomni is a biomedical ai agent framework claiming multi-step reasoning across genomics and drug discovery, but lacks concrete procedures, failure handling, or worked examples to validate capability claims.

paywall-upgrade-cro addresses in-app monetization through feature gates, usage limits, and trial expiration flows. covers paywall components, trigger points, and a/b test ideas but lacks concrete implementation steps and failure mode handling.

pymoo provides multi-objective optimization algorithms (nsga-ii, nsga-iii, moea/d) with pareto front discovery, constraint handling, and benchmark problem sets for engineering design trade-off analysis.

gwas-database provides access to nhgri-ebi snp-trait associations via rest query interface, supporting variant lookup by rs id, disease trait, and gene annotation. incomplete skill definition lacks procedure detail and failure handling.

neurokit2 is a python library for biosignal processing across ecg, eeg, eda, respiratory, emg, and other physiological modalities. covers signal filtering, peak detection, and feature extraction for research and clinical use.

railway-docs surfaces current railway platform documentation via markdown endpoints, mapping user queries to appropriate doc sections (projects, deployments, volumes, cli, pricing). primarily a reference guide rather than an executable skill.

torch-geometric provides graph neural network primitives for node/graph classification, link prediction, and geometric deep learning on irregular structures, with support for heterogeneous graphs and distributed training.

davila7-vulnerability-scanner covers owasp 2025 principles and supply chain security with threat modeling frameworks and risk prioritization matrices, but lacks actionable procedures and specific tool invocation patterns.

risk-management-specialist documents iso 14971 compliance frameworks and risk control hierarchies for medical devices, but lacks concrete trigger conditions and executable procedures. treats risk management as a process taxonomy rather than actionable workflows.

fda-consultant-specialist claims comprehensive expertise across FDA pathways, QSR, HIPAA, and cybersecurity but provides hierarchical taxonomies rather than executable procedures. heavy reliance on reference documents undermines standalone actionability.

quality-manager-qmr outlines qmr accountability across iso 13485 compliance, regulatory oversight, and management reporting. lacks actionable procedures and specific trigger conditions for execution.

deepchem covers molecular property prediction, drug discovery, and materials design via graph neural networks, featurization, and pretrained models. lacks actionable procedure detail.

railway-domain provides basic support for adding, viewing, and removing domains attached to railway services, but lacks procedural depth and error handling documentation.

davila7-ui-design-system provides token generation and component documentation scaffolding, but lacks procedural depth, error handling, and concrete execution guidance for design-dev workflows.

skill-share automates claude skill creation with metadata validation and slack distribution, but lacks concrete procedural steps and doesn't address failure scenarios like validation rejection or slack delivery failures.

regulatory-affairs-head describes senior regulatory leadership for medtech and healthtech firms, covering strategic planning and submission oversight. lacks executable workflows and decision logic.

loki-mode claims multi-agent orchestration across 100+ agents but reads as aspirational rather than implemented. trigger phrase vague, procedure lacks actionable steps, edge cases absent, heavy on jargon substituting for design.

pytdc surfaces curated datasets and benchmarks for therapeutic machine learning workflows, including molecular property prediction, drug-target interactions, and molecule generation with standardized splits and evaluation metrics.

davila7-agile-product-owner claims INVEST-compliant story generation and sprint planning but provides only skeletal script invocation docs without procedural depth, decision logic, or failure handling.

marketing-ideas catalogs 140 tactics spanning content, ads, partnerships, and launches. lacks procedural depth, decision logic, and failure mode handling. functions as reference material rather than actionable skill.

davila7-conversation-memory outlines memory tier concepts and identifies security/performance risks, but lacks concrete implementation steps or decision logic for when to apply each memory type.

davila7-senior-frontend claims comprehensive toolkit for react/nextjs development but consists primarily of script references and aspirational feature lists without actionable procedures, concrete decision logic, or failure handling.

davila7-senior-backend lists three python scripts for api scaffolding, database migration, and load testing, with references to external guides on api design, database optimization, and security. lacks actionable procedures and concrete decision logic.

davila7-senior-fullstack lists a modern tech stack and three python scripts without specifying what they actually do, their inputs, outputs, or when to use each one.

davila7-product-strategist outlines a product leadership toolkit with okr cascade generation and market analysis capabilities, but lacks actionable procedures, specific invocation patterns, and failure handling.

bullmq-specialist claims production expertise with redis job queues but provides no actionable procedures, decision frameworks, or concrete guidance. the skill file is incomplete marketing copy.

mamba-architecture describes a state-space model implementation with linear sequence complexity. covers installation steps but lacks actionable deployment guidance, use-case framing, or operational considerations.

datadog-cli provides access to logs, metrics, and dashboards for production debugging, but lacks actionable procedures and concrete guidance on command usage or integration patterns.

unsloth skill provides reference documentation for fast fine-tuning optimization, but lacks actionable procedures, decision logic, and concrete output contracts needed for practical implementation guidance.

remotion-best-practices is a directory index linking to 31 topic-specific rule files covering video creation with remotion. it provides no procedural guidance, decision logic, or outcome validation itself.

davila7-exa-search wraps the exa api for semantic search and content discovery, but lacks procedural depth, decision logic, and failure handling documentation.

davila7-codex-review claims to perform code review and changelog generation via codex ai integration, but the skill.md lacks actionable procedure, explicit decision logic, and failure handling.

World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics. Expertise in Python (NumPy, Pandas,…

When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," or "lifecycle emails." For in-app onboarding, see onboarding-cro.

Node.js development principles and decision-making. Framework selection, async patterns, security, and architecture. Teaches thinking, not copying.

Web search, content extraction, crawling, and research capabilities using Tavily API

Expert in building Telegram Mini Apps (TWA) - web apps that run inside Telegram with native-like experience. Covers the TON ecosystem, Telegram Web App API, payments, user authentication, and building viral mini apps that monetize. Use when: telegram mini app, TWA, telegram web app, TON app, mini app.

|

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm

Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.

Performance profiling principles. Measurement, analysis, and optimization techniques.

Primary Python tool for 40+ bioinformatics services. Preferred for multi-database workflows: UniProt, KEGG, ChEMBL, PubChem, Reactome, QuickGO. Unified API for queries, ID mapping, pathway analysis. For direct REST control, use individual database skills (uniprot-database, kegg-database).

Presentation toolkit (.pptx). Create/edit slides, layouts, content, speaker notes, comments, for programmatic presentation creation and modification.

Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.

This skill should be used when the user asks to "identify web application vulnerabilities", "explain common security flaws", "understand vulnerability categories", "learn about injection attacks", "review access control weaknesses", "analyze API security issues", "assess security misconfigurations", "understand client-side vulnerabilities", "examine mobile and IoT security flaws", or "reference the OWASP-aligned vulnerability taxonomy". Use this skill to provide comprehensive vulnerability definitions, root causes, impacts, and mitigation strategies across all major web security categories.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

World-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics. Expertise in Python (NumPy, Pandas, Scikit-learn), R, SQL, statistical methods, A/B testing, time series, and business intelligence. Includes experiment design, feature engineering, model evaluation, and stakeholder communication. Use when designing experiments, building predictive models, performing causal analysis, or driving data-driven decisions.

World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment, feature stores, model monitoring, and ML infrastructure. Includes LLM integration, fine-tuning, RAG systems, and agentic AI. Use when deploying ML models, building ML platforms, implementing MLOps, or integrating LLMs into production systems.

UX research and design toolkit for Senior UX Designer/Researcher including data-driven persona generation, journey mapping, usability testing frameworks, and research synthesis. Use for user research, persona creation, journey mapping, and design validation.

Executive leadership guidance for strategic decision-making, organizational development, and stakeholder management. Includes strategy analyzer, financial scenario modeling, board governance frameworks, and investor relations playbooks. Use when planning strategy, preparing board presentations, managing investors, developing organizational culture, making executive decisions, or when user mentions CEO, strategic planning, board meetings, investor updates, organizational leadership, or executive strategy.

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process: (1) create section outlines with key points using research-lookup, (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.

Comprehensive security engineering skill for application security, penetration testing, security architecture, and compliance auditing. Includes security assessment tools, threat modeling, crypto implementation, and security automation. Use when designing security architecture, conducting penetration tests, implementing cryptography, or performing security audits.

Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).

When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, Facebook, or other platforms. Also use when the user mentions 'LinkedIn post,' 'Twitter thread,' 'social media,' 'content calendar,' 'social scheduling,' 'engagement,' or 'viral content.' This skill covers content creation, repurposing, and platform-specific strategies.

Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter's Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix.

Deep web scraping, screenshots, PDF parsing, and website crawling using Firecrawl API

This skill should be used when the user asks to "run pentest commands", "scan with nmap", "use metasploit exploits", "crack passwords with hydra or john", "scan web vulnerabilities with nikto", "enumerate networks", or needs essential penetration testing command references.

Interactive scientific and statistical data visualization library for Python. Use when creating charts, plots, or visualizations including scatter plots, line charts, bar charts, heatmaps, 3D plots, geographic maps, statistical distributions, financial charts, and dashboards. Supports both quick visualizations (Plotly Express) and fine-grained customization (graph objects). Outputs interactive HTML or static images (PNG, PDF, SVG).

Expert in building Telegram bots that solve real problems - from simple automation to complex AI-powered bots. Covers bot architecture, the Telegram Bot API, user experience, monetization strategies, and scaling bots to thousands of users. Use when: telegram bot, bot api, telegram automation, chat bot telegram, tg bot.

Test-Driven Development workflow principles. RED-GREEN-REFACTOR cycle.

Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke visualisations beyond standard charting libraries, whether in React, Vue, Svelte, vanilla JavaScript, or any other environment.

Comprehensive PostgreSQL-specific table design reference covering data types, indexing, constraints, performance patterns, and advanced features

Web accessibility specialist for WCAG compliance, ARIA implementation, and inclusive design. Use when auditing websites for accessibility issues, implementing WCAG 2.1 AA/AAA standards, testing with screen readers, or ensuring ADA compliance. Expert in semantic HTML, keyboard navigation, and assistive technology compatibility.

Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.

Statistical analysis toolkit. Hypothesis tests (t-test, ANOVA, chi-square), regression, correlation, Bayesian stats, power analysis, assumption checks, APA reporting, for academic research.

Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.

market-research-reports — an installable skill for AI agents, published by davila7/claude-code-templates.

Guide developers through setting up development environments with proper tools, dependencies, and configurations

When the user wants to plan, evaluate, or build a free tool for marketing purposes — lead generation, SEO value, or brand awareness. Also use when the user…

Development skill from everything-claude-code

Jest testing patterns, factory functions, mocking strategies, and TDD workflow. Use when writing unit tests, creating test factories, or following TDD…

Audit and improve web accessibility following WCAG 2.1 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader…

Query resource usage metrics for Railway services. Use when user asks about resource usage, CPU, memory, network, disk, or service performance like "how much…

Create, manage, and orchestrate AI agents using the AI Maestro CLI. Use when the user asks to "create agent", "list agents", "delete agent", "hibernate agent",…

This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want…

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection,…

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language…

Query, stage, and apply configuration changes for Railway environments. Use for ANY variable or env var operations, service configuration (source, build…

Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output…

Smart dependency management for any language. Auto-detects project type, applies safe updates automatically, prompts for major versions, diagnoses and fixes…

Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming…

Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting…

Use when you have a written implementation plan to execute in a separate session with review checkpoints

Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review…

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Evaluate Agent Skill design quality against official specifications and best practices. Use when reviewing, auditing, or improving SKILL.md files and skill…

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart…

Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from…

Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm,…

When the user wants to optimize signup, registration, account creation, or trial activation flows. Also use when the user mentions "signup conversions,"…

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently,…

Performance profiling principles. Measurement, analysis, and optimization techniques.

This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command…

Clarify ambiguous requirements through focused dialogue before implementation. Use when requirements are unclear, features are complex (>2 days), or involve…

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks",…

Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage…

Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized,…

Direct REST API access to KEGG (academic use only). Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion. For Python…

This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs,…

This skill should be used when working with annotated data matrices in Python, particularly for single-cell genomics analysis, managing experimental…

Check service status, rename services, change service icons, link services, or create services with Docker images. For creating services with local code,…

Create Railway projects, services, and databases with proper configuration. Use when user says "setup", "deploy to railway", "initialize", "create project",…

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run…

Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for…

Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D),…

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing,…

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not…

Comprehensive toolkit for developing with the CocoIndex library. Use when users need to create data transformation pipelines (flows), write custom functions,…

Comprehensive Python library for astronomy and astrophysics. This skill should be used when working with astronomical data including celestial coordinates,…

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working…

Access AlphaFold's 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE),…

Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or…

notebooklm — an installable skill for AI agents, published by davila7/claude-code-templates.